HumanCompatibleAI / Imitation
Licence: mit
Clean PyTorch implementations of imitation learning algorithms
Stars: ✭ 204
Programming Languages
python
139335 projects - #7 most used programming language
Labels
Projects that are alternatives of or similar to Imitation
Deterministic Gail Pytorch
PyTorch implementation of Deterministic Generative Adversarial Imitation Learning (GAIL) for Off Policy learning
Stars: ✭ 44 (-78.43%)
Mutual labels: imitation-learning
Ngsim env
Learning human driver models from NGSIM data with imitation learning.
Stars: ✭ 96 (-52.94%)
Mutual labels: imitation-learning
Coach
Reinforcement Learning Coach by Intel AI Lab enables easy experimentation with state of the art Reinforcement Learning algorithms
Stars: ✭ 2,085 (+922.06%)
Mutual labels: imitation-learning
Imitation Learning Dagger Torcs
A Simple Example for Imitation Learning with Dataset Aggregation (DAGGER) on Torcs Env
Stars: ✭ 60 (-70.59%)
Mutual labels: imitation-learning
Imitation Learning
Imitation learning algorithms
Stars: ✭ 85 (-58.33%)
Mutual labels: imitation-learning
Easy Rl
强化学习中文教程，在线阅读地址：https://datawhalechina.github.io/easy-rl/
Stars: ✭ 3,004 (+1372.55%)
Mutual labels: imitation-learning
Babyai
BabyAI platform. A testbed for training agents to understand and execute language commands.
Stars: ✭ 490 (+140.2%)
Mutual labels: imitation-learning
Hand dapg
Repository to accompany RSS 2018 paper on dexterous hand manipulation
Stars: ✭ 88 (-56.86%)
Mutual labels: imitation-learning
Gym Carla
An OpenAI gym wrapper for CARLA simulator
Stars: ✭ 164 (-19.61%)
Mutual labels: imitation-learning
Imitation Learning
Autonomous driving: Tensorflow implementation of the paper "End-to-end Driving via Conditional Imitation Learning"
Stars: ✭ 60 (-70.59%)
Mutual labels: imitation-learning
Inverse rl
Adversarial Imitation Via Variational Inverse Reinforcement Learning
Stars: ✭ 79 (-61.27%)
Mutual labels: imitation-learning
Learningbycheating
Driving in CARLA using waypoint prediction and two-stage imitation learning
Stars: ✭ 119 (-41.67%)
Mutual labels: imitation-learning
Pgdrive
PGDrive: an open-ended driving simulator with infinite scenes from procedural generation
Stars: ✭ 60 (-70.59%)
Mutual labels: imitation-learning
Carla
Open-source simulator for autonomous driving research.
Stars: ✭ 7,012 (+3337.25%)
Mutual labels: imitation-learning
Gail ppo tf
Tensorflow implementation of Generative Adversarial Imitation Learning(GAIL) with discrete action
Stars: ✭ 99 (-51.47%)
Mutual labels: imitation-learning
My bibliography for research on autonomous driving
Personal notes about scientific and research works on "Decision-Making for Autonomous Driving"
Stars: ✭ 197 (-3.43%)
Mutual labels: imitation-learning
Gail Tf
Tensorflow implementation of generative adversarial imitation learning
Stars: ✭ 179 (-12.25%)
Mutual labels: imitation-learning
Ravens
Train robotic agents to learn pick and place with deep learning for vision-based manipulation in PyBullet. Transporter Nets, CoRL 2020.
Stars: ✭ 133 (-34.8%)
Mutual labels: imitation-learning
Imitation Learning Baseline Implementations
This project aims to provide clean implementations of imitation learning algorithms. Currently we have implementations of Behavioral Cloning, DAgger (with synthetic examples), Adversarial Inverse Reinforcement Learning, and Generative Adversarial Imitation Learning.
Installation:
Installing PyPI release
pip install imitation
Install latest commit
git clone http://github.com/HumanCompatibleAI/imitation
cd imitation
pip install -e .
Optional Mujoco Dependency:
Follow instructions to install mujoco_py v1.5 here.
CLI Quickstart:
We provide several CLI scripts as a front-end to the algorithms implemented in imitation. These use Sacred for configuration and replicability.
# Train PPO agent on cartpole and collect expert demonstrations. Tensorboard logs saved in `quickstart/rl/`
python -m imitation.scripts.expert_demos with fast cartpole log_dir=quickstart/rl/
# Train GAIL from demonstrations. Tensorboard logs saved in output/ (default log directory).
python -m imitation.scripts.train_adversarial with fast gail cartpole rollout_path=quickstart/rl/rollouts/final.pkl
# Train AIRL from demonstrations. Tensorboard logs saved in output/ (default log directory).
python -m imitation.scripts.train_adversarial with fast airl cartpole rollout_path=quickstart/rl/rollouts/final.pkl
Tips:
- Remove the "fast" option from the commands above to allow training run to completion.
-
python -m imitation.scripts.expert_demos print_configwill list Sacred script options. These configuration options are documented in each script's docstrings.
For more information on how to configure Sacred CLI options, see the Sacred docs.
Python Interface Quickstart:
See examples/quickstart.py for an example script that loads CartPole-v1 demonstrations and trains BC, GAIL, and AIRL models on that data.
Density reward baseline
We also implement a density-based reward baseline. You can find an example notebook here.
Citations (BibTeX)
@misc{wang2020imitation,
author = {Wang, Steven and Toyer, Sam and Gleave, Adam and Emmons, Scott},
title = {The {\tt imitation} Library for Imitation Learning and Inverse Reinforcement Learning},
year = {2020},
publisher = {GitHub},
journal = {GitHub repository},
howpublished = {\url{https://github.com/HumanCompatibleAI/imitation}},
}
Contributing
See CONTRIBUTING.md.
Note that the project description data, including the texts, logos, images, and/or trademarks,
for each open source project belongs to its rightful owner.
If you wish to add or remove any projects, please contact us at [email protected].